Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nicht
    -0.07
    'im
    -0.06
    icum
    -0.06
    enia
    -0.06
    UFFIX
    -0.06
     Мик
    -0.06
    _mid
    -0.06
    Coupon
    -0.06
     Patient
    -0.06
    ицин
    -0.06
    POSITIVE LOGITS
    digital
    0.07
     tricks
    0.07
     چرخ
    0.07
    -wage
    0.06
     substantial
    0.06
    鲜
    0.06
    _yes
    0.06
     shot
    0.06
     pristine
    0.06
     shutdown
    0.06
    Act Density 0.007%

    No Known Activations